Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of authority or control exerted by entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    entities following "by" or "with"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.57
     antidesliz
    -0.47
    Personensuche
    -0.45
     cristales
    -0.45
     Vordergrund
    -0.44
     propOrder
    -0.44
     borboleta
    -0.42
    eclared
    -0.40
     quema
    -0.40
    一身
    -0.40
    POSITIVE LOGITS
     governments
    1.05
     pemerintah
    0.88
     Governments
    0.85
     universities
    0.83
     regulators
    0.79
     manufacturers
    0.79
     insurers
    0.79
     advertisers
    0.79
     publishers
    0.78
     authorities
    0.77
    Act Density 0.125%

    No Known Activations